© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64533
    Prev
    Next
    INDEX
    Explanations

    generation

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on numeric or alphanumeric identifiers (e.g. generation labels, model numbers, and other digit‐containing tokens).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     adresa
    -0.86
     thánh
    -0.79
    句子
    -0.77
     原
    -0.76
    泯
    -0.74
     configurar
    -0.74
    %@",
    -0.73
    原
    -0.73
    zate
    -0.73
     medo
    -0.73
    POSITIVE LOGITS
     generation
    1.48
     generations
    1.42
     generación
    1.38
     Generation
    1.34
     Gen
    1.32
     geração
    1.29
    Generation
    1.24
     generasi
    1.24
     générations
    1.23
     gen
    1.14
    Activations Density 0.025%

    No Known Activations